{"id":"https://openalex.org/W4415003581","doi":"https://doi.org/10.1109/acit65614.2025.11185827","title":"AI-Driven OCR in Practice: Assessing ChatGPT-4o and Google Vision as Alternatives to Manual Optical Character Recognition","display_name":"AI-Driven OCR in Practice: Assessing ChatGPT-4o and Google Vision as Alternatives to Manual Optical Character Recognition","publication_year":2025,"publication_date":"2025-09-17","ids":{"openalex":"https://openalex.org/W4415003581","doi":"https://doi.org/10.1109/acit65614.2025.11185827"},"language":"en","primary_location":{"id":"doi:10.1109/acit65614.2025.11185827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acit65614.2025.11185827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 15th International Conference on Advanced Computer Information Technologies (ACIT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093078368","display_name":"Serhii Robotko","orcid":"https://orcid.org/0000-0002-9203-8385"},"institutions":[{"id":"https://openalex.org/I13779751","display_name":"Admiral Makarov National University of Shipbuilding","ror":"https://ror.org/04ymc1w90","country_code":"UA","type":"education","lineage":["https://openalex.org/I13779751"]}],"countries":["UA"],"is_corresponding":true,"raw_author_name":"Serhii Robotko","raw_affiliation_strings":["Admiral Makarov National University of Shipbuilding,Automation And Computer-Integrated Technologies,Mykolaiv,Ukraine"],"affiliations":[{"raw_affiliation_string":"Admiral Makarov National University of Shipbuilding,Automation And Computer-Integrated Technologies,Mykolaiv,Ukraine","institution_ids":["https://openalex.org/I13779751"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5093078368"],"corresponding_institution_ids":["https://openalex.org/I13779751"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2225302,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"944","last_page":"947"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9175999760627747,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9175999760627747,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7426000237464905},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.5860000252723694},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5091999769210815},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.47600001096725464},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4740999937057495},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.43790000677108765},{"id":"https://openalex.org/keywords/stylized-fact","display_name":"Stylized fact","score":0.41040000319480896},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3732999861240387}],"concepts":[{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7426000237464905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7378000020980835},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.5860000252723694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5515999794006348},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5091999769210815},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.43790000677108765},{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3732999861240387},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3727000057697296},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3513999879360199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C169806903","wikidata":"https://www.wikidata.org/wiki/Q5937752","display_name":"Human error","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.33180001378059387},{"id":"https://openalex.org/C164112704","wikidata":"https://www.wikidata.org/wiki/Q7974348","display_name":"Watermark","level":3,"score":0.3228999972343445},{"id":"https://openalex.org/C107645774","wikidata":"https://www.wikidata.org/wiki/Q5467169","display_name":"Human resources","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3109999895095825},{"id":"https://openalex.org/C2779332521","wikidata":"https://www.wikidata.org/wiki/Q1820694","display_name":"Legibility","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C46934059","wikidata":"https://www.wikidata.org/wiki/Q61515","display_name":"Outsourcing","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acit65614.2025.11185827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acit65614.2025.11185827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 15th International Conference on Advanced Computer Information Technologies (ACIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Optical":[0],"Character":[1],"Recognition":[2],"(OCR)":[3],"remains":[4],"heavily":[5],"reliant":[6],"on":[7,89,111,221],"human":[8,52,80,200,252],"labor":[9],"in":[10,20],"many":[11],"industries,":[12],"from":[13,159],"policing":[14],"intellectual":[15],"property":[16],"(e.g.":[17,177,186],"identifying":[18],"text":[19,181],"logos)":[21],"to":[22,49,164,199],"banking":[23],"and":[24,30,35,70,96,107,139,155,173,182,184,195,207,217,226,229,240],"government":[25],"document":[26],"verification.":[27],"Manual":[28],"transcription":[29],"validation":[31],"incur":[32],"high":[33],"costs":[34,151],"slow":[36],"turnaround":[37],"times,":[38,243],"yet":[39],"organizations":[40],"demand":[41],"near-perfect":[42],"accuracy":[43,198],"that":[44,60,121,144],"traditional":[45,251],"OCR":[46,81,101,150],"often":[47],"fails":[48],"deliver":[50],"without":[51],"oversight":[53],"[1].":[54],"This":[55],"paper":[56],"explores":[57],"the":[58,112,129,136,145,218],"hypothesis":[59],"recent":[61],"AI":[62,123,216],"vision":[63,67],"tools\u2014specifically":[64],"OpenAI\u2019s":[65],"ChatGPT-4":[66],"model":[68],"(ChatGPT-4o)":[69],"Google":[71,108,174,227],"Cloud":[72],"Vision":[73,109,228],"API\u2014can":[74],"replace":[75],"a":[76],"significant":[77],"portion":[78],"of":[79,128,161,167,179,248],"work.":[82],"We":[83,142,203],"evaluate":[84],"an":[85,245],"automated":[86],"dual-OCR":[87],"approach":[88,234],"155,000":[90],"mixed-language":[91],"images":[92,130],"(logos,":[93],"short":[94],"notes,":[95],"words).":[97],"The":[98,169],"method":[99],"accepts":[100],"results":[102,119],"only":[103],"when":[104,213],"both":[105],"ChatGPT-4o":[106,172,225],"agree":[110],"recognized":[113],"text,":[114],"significantly":[115,235],"boosting":[116],"reliability.":[117],"Our":[118],"show":[120],"this":[122],"ensemble":[124],"automatically":[125],"processed":[126],"69%":[127],"correctly.":[131],"Two":[132],"performance":[133],"tables":[134],"detail":[135],"match":[137],"rates":[138],"cost":[140],"analysis.":[141],"find":[143],"AI-driven":[146],"process":[147],"can":[148],"cut":[149],"by":[152],"over":[153],"40%":[154],"compress":[156],"project":[157],"durations":[158],"weeks":[160],"manual":[162],"work":[163],"mere":[165],"hours":[166],"computation.":[168],"discussion":[170],"contrasts":[171],"Vision\u2019s":[175],"strengths":[176],"handling":[178],"stylized":[180],"handwriting)":[183],"weaknesses":[185],"certain":[187],"symbols,":[188],"uncommon":[189],"scripts,":[190],"or":[191],"image":[192],"quality":[193],"issues),":[194],"compares":[196],"their":[197],"error":[201],"rates.":[202],"also":[204],"consider":[205],"ethical":[206],"operational":[208],"factors,":[209],"including":[210],"data":[211],"privacy":[212],"using":[214],"cloud":[215],"potential":[219],"impact":[220],"jobs.":[222],"By":[223],"combining":[224],"validating":[230],"matched":[231],"results,":[232],"our":[233],"reduces":[236],"costs,":[237],"enhances":[238],"accuracy,":[239],"accelerates":[241],"processing":[242],"marking":[244],"ongoing":[246],"trend":[247],"automation":[249],"replacing":[250],"tasks.":[253]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
